Text-to-SQL emerges to play an important role in interactive data analysis, which provides a friendly interface for converting natural language into relational database language (i.e., SQL). In order to translate a user’s query into an executable SQL statement, semantic parsing is essential to the transformation process. In particular, existing efforts provide some feasible solutions, and state-of-the-art models mainly adopt the sketch-based paradigm such that template values are to be filled. To this end, most methods extract values based on column representations. However, if the query contains multiple values that belong to different columns, these methods may fail to extract the values accurately. Moreover, it can be difficult to infer the right values when the query does not explicitly mention the corresponding column names. To bridge the gap, we propose a novel neural architecture, namely, ER-SQL for learning enhanced representations for Text-to-SQL. Based on pre-trained model BERT, ER-SQL uses column contents to better extract features of columns. Moreover, ER-SQL harnesses the column representations to latently reformulate the query. To verify the effectiveness of ER-SQL, comprehensive experiments demonstrate that ER-SQL achieves better results than existing models on the benchmark dataset WikiSQL, as well as on a representative Chinese dataset TableQA.

Text-to-SQL 的出现在交互式数据分析中扮演着重要的角色，它为将自然语言转换为关系数据库语言（即 SQL）提供了一个友好的界面。为了将用户的查询转换为可执行的 SQL 语句，语义解析对于转换过程至关重要。特别是现有的努力提供了一些可行的解决方案，最先进的模型主要采用基于草图的范式，以便填充模板值。为此，大多数方法基于列表示提取值。但是，如果查询包含属于不同列的多个值，这些方法可能无法准确提取值。此外，当查询未明确提及相应的列名时，可能很难推断出正确的值。为了弥补差距，ER-SQL用于学习 Text-to-SQL 的增强表示。基于预训练模型BERT，ER-SQL使用列内容来更好地提取列的特征。此外，ER-SQL利用列表示来潜在地重新制定查询。为了验证ER-SQL的有效性，综合实验表明ER-SQL在基准数据集WikiSQL以及具有代表性的中文数据集TableQA上取得了比现有模型更好的结果。